End of training

README.md

@@ -1,199 +1,141 @@
 ---
 library_name: transformers
-tags: []
+license: cc-by-nc-4.0
+base_model: facebook/mms-1b-all
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: ssc-meh-mms-model-mix-adapt-max3-devtrain
+  results: []
 ---
 
-# Model Card for Model ID
-
-<!-- Provide a quick summary of what the model is/does. -->
-
-
-
-## Model Details
-
-### Model Description
-
-<!-- Provide a longer summary of what this model is. -->
-
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-
-### Model Sources [optional]
-
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
-
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# ssc-meh-mms-model-mix-adapt-max3-devtrain
+
+This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4734
+- Cer: 0.1554
+- Wer: 0.4442
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0005
+- train_batch_size: 8
+- eval_batch_size: 6
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 20
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch   | Step  | Validation Loss | Cer    | Wer    |
+|:-------------:|:-------:|:-----:|:---------------:|:------:|:------:|
+| 0.9238        | 0.2625  | 200   | 0.6740          | 0.1978 | 0.6038 |
+| 0.7722        | 0.5249  | 400   | 0.6028          | 0.1819 | 0.5251 |
+| 0.6953        | 0.7874  | 600   | 0.5849          | 0.1787 | 0.4990 |
+| 0.6484        | 1.0499  | 800   | 0.5523          | 0.1725 | 0.4792 |
+| 0.639         | 1.3123  | 1000  | 0.6054          | 0.1765 | 0.5020 |
+| 0.6618        | 1.5748  | 1200  | 0.5632          | 0.1751 | 0.4775 |
+| 0.6454        | 1.8373  | 1400  | 0.6640          | 0.1862 | 0.5266 |
+| 0.6222        | 2.0997  | 1600  | 0.6218          | 0.1781 | 0.5051 |
+| 0.6014        | 2.3622  | 1800  | 0.6539          | 0.1815 | 0.5191 |
+| 0.5992        | 2.6247  | 2000  | 0.6177          | 0.1830 | 0.5165 |
+| 0.6144        | 2.8871  | 2200  | 0.5944          | 0.1812 | 0.5099 |
+| 0.5796        | 3.1496  | 2400  | 0.5814          | 0.1874 | 0.5379 |
+| 0.5781        | 3.4121  | 2600  | 0.5527          | 0.1773 | 0.5010 |
+| 0.5728        | 3.6745  | 2800  | 0.5361          | 0.1763 | 0.4950 |
+| 0.5911        | 3.9370  | 3000  | 0.5411          | 0.1731 | 0.4810 |
+| 0.5577        | 4.1995  | 3200  | 0.5887          | 0.1817 | 0.5177 |
+| 0.5537        | 4.4619  | 3400  | 0.5406          | 0.1748 | 0.4901 |
+| 0.5466        | 4.7244  | 3600  | 0.5576          | 0.1728 | 0.4816 |
+| 0.5896        | 4.9869  | 3800  | 0.5349          | 0.1703 | 0.4741 |
+| 0.5497        | 5.2493  | 4000  | 0.5584          | 0.1730 | 0.4836 |
+| 0.5578        | 5.5118  | 4200  | 0.5642          | 0.1673 | 0.4506 |
+| 0.5431        | 5.7743  | 4400  | 0.6210          | 0.1736 | 0.4811 |
+| 0.5296        | 6.0367  | 4600  | 0.5038          | 0.1669 | 0.4631 |
+| 0.5423        | 6.2992  | 4800  | 0.5106          | 0.1632 | 0.4522 |
+| 0.5293        | 6.5617  | 5000  | 0.5162          | 0.1641 | 0.4481 |
+| 0.5221        | 6.8241  | 5200  | 0.5315          | 0.1711 | 0.4777 |
+| 0.5033        | 7.0866  | 5400  | 0.4914          | 0.1614 | 0.4423 |
+| 0.5361        | 7.3491  | 5600  | 0.4944          | 0.1617 | 0.4429 |
+| 0.5044        | 7.6115  | 5800  | 0.5231          | 0.1622 | 0.4530 |
+| 0.509         | 7.8740  | 6000  | 0.5043          | 0.1602 | 0.4504 |
+| 0.5165        | 8.1365  | 6200  | 0.5099          | 0.1693 | 0.4793 |
+| 0.5003        | 8.3990  | 6400  | 0.5075          | 0.1662 | 0.4614 |
+| 0.5111        | 8.6614  | 6600  | 0.5185          | 0.1637 | 0.4580 |
+| 0.472         | 8.9239  | 6800  | 0.5178          | 0.1686 | 0.4804 |
+| 0.507         | 9.1864  | 7000  | 0.4922          | 0.1581 | 0.4344 |
+| 0.4879        | 9.4488  | 7200  | 0.5215          | 0.1628 | 0.4509 |
+| 0.4944        | 9.7113  | 7400  | 0.5178          | 0.1700 | 0.4870 |
+| 0.4864        | 9.9738  | 7600  | 0.5039          | 0.1633 | 0.4559 |
+| 0.4813        | 10.2362 | 7800  | 0.4907          | 0.1606 | 0.4486 |
+| 0.4602        | 10.4987 | 8000  | 0.5027          | 0.1606 | 0.4511 |
+| 0.4991        | 10.7612 | 8200  | 0.5284          | 0.1733 | 0.4970 |
+| 0.4875        | 11.0236 | 8400  | 0.4942          | 0.1626 | 0.4597 |
+| 0.4579        | 11.2861 | 8600  | 0.5062          | 0.1625 | 0.4675 |
+| 0.4683        | 11.5486 | 8800  | 0.4967          | 0.1626 | 0.4610 |
+| 0.4483        | 11.8110 | 9000  | 0.4948          | 0.1636 | 0.4648 |
+| 0.4702        | 12.0735 | 9200  | 0.4915          | 0.1631 | 0.4638 |
+| 0.4648        | 12.3360 | 9400  | 0.5019          | 0.1629 | 0.4646 |
+| 0.4639        | 12.5984 | 9600  | 0.4935          | 0.1593 | 0.4509 |
+| 0.4534        | 12.8609 | 9800  | 0.5004          | 0.1640 | 0.4650 |
+| 0.4411        | 13.1234 | 10000 | 0.4891          | 0.1552 | 0.4332 |
+| 0.4508        | 13.3858 | 10200 | 0.5215          | 0.1647 | 0.4743 |
+| 0.4586        | 13.6483 | 10400 | 0.4917          | 0.1540 | 0.4331 |
+| 0.4597        | 13.9108 | 10600 | 0.4734          | 0.1539 | 0.4315 |
+| 0.4499        | 14.1732 | 10800 | 0.4969          | 0.1638 | 0.4677 |
+| 0.4429        | 14.4357 | 11000 | 0.4786          | 0.1558 | 0.4372 |
+| 0.4385        | 14.6982 | 11200 | 0.4930          | 0.1602 | 0.4527 |
+| 0.4275        | 14.9606 | 11400 | 0.4914          | 0.1578 | 0.4482 |
+| 0.4263        | 15.2231 | 11600 | 0.4780          | 0.1550 | 0.4362 |
+| 0.4332        | 15.4856 | 11800 | 0.4792          | 0.1576 | 0.4468 |
+| 0.4408        | 15.7480 | 12000 | 0.4844          | 0.1570 | 0.4470 |
+| 0.4475        | 16.0105 | 12200 | 0.4951          | 0.1595 | 0.4575 |
+| 0.4212        | 16.2730 | 12400 | 0.4832          | 0.1558 | 0.4398 |
+| 0.4402        | 16.5354 | 12600 | 0.4920          | 0.1593 | 0.4561 |
+| 0.4206        | 16.7979 | 12800 | 0.4781          | 0.1565 | 0.4491 |
+| 0.4054        | 17.0604 | 13000 | 0.4814          | 0.1581 | 0.4514 |
+| 0.4147        | 17.3228 | 13200 | 0.4853          | 0.1590 | 0.4627 |
+| 0.4155        | 17.5853 | 13400 | 0.4767          | 0.1569 | 0.4503 |
+| 0.4213        | 17.8478 | 13600 | 0.4920          | 0.1611 | 0.4668 |
+| 0.4076        | 18.1102 | 13800 | 0.4806          | 0.1560 | 0.4470 |
+| 0.4028        | 18.3727 | 14000 | 0.4880          | 0.1600 | 0.4621 |
+| 0.4129        | 18.6352 | 14200 | 0.4725          | 0.1540 | 0.4393 |
+| 0.4172        | 18.8976 | 14400 | 0.4741          | 0.1554 | 0.4447 |
+| 0.407         | 19.1601 | 14600 | 0.4779          | 0.1564 | 0.4473 |
+| 0.4109        | 19.4226 | 14800 | 0.4750          | 0.1554 | 0.4435 |
+| 0.4085        | 19.6850 | 15000 | 0.4739          | 0.1559 | 0.4456 |
+| 0.4123        | 19.9475 | 15200 | 0.4734          | 0.1554 | 0.4442 |
+
+
+### Framework versions
+
+- Transformers 4.52.1
+- Pytorch 2.9.1+cu128
+- Datasets 3.6.0
+- Tokenizers 0.21.4

adapter.meh.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad7d1815210ce4c3fe213a18e6746404c72e6cccfb190d8b3875a72070a96166
+size 8972764

config.json

@@ -0,0 +1,107 @@
+{
+  "activation_dropout": 0.05,
+  "adapter_attn_dim": 16,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 1024,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.05,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1280,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 48,
+  "num_negatives": 100,
+  "output_hidden_size": 1280,
+  "pad_token_id": 62,
+  "proj_codevector_dim": 1024,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.1",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 65,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad11248402e3712699df355894107e57e7236bce19fce5ecd04d2f12f67fd733
+size 3859065140

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d480f82b5b20a03bad7518ca6ba967198a723cc9bcbb1011a25d310d60c16ba
+size 5969

vocab.json

@@ -1,67 +1 @@
-{
-  "meh": {
-    "'": 21,
-    ".": 3,
-    "...": 60,
-    "A": 17,
-    "D": 10,
-    "E": 14,
-    "F": 55,
-    "H": 57,
-    "I": 27,
-    "J": 56,
-    "K": 13,
-    "L": 41,
-    "M": 40,
-    "N": 6,
-    "O": 47,
-    "P": 19,
-    "R": 42,
-    "S": 4,
-    "T": 22,
-    "U": 12,
-    "V": 30,
-    "W": 39,
-    "X": 43,
-    "Y": 25,
-    "[PAD]": 62,
-    "[UNK]": 61,
-    "a": 16,
-    "b": 37,
-    "c": 15,
-    "d": 38,
-    "e": 1,
-    "f": 9,
-    "g": 58,
-    "h": 34,
-    "i": 0,
-    "j": 35,
-    "k": 31,
-    "l": 23,
-    "m": 5,
-    "n": 49,
-    "o": 44,
-    "p": 32,
-    "q": 20,
-    "r": 11,
-    "s": 29,
-    "t": 54,
-    "u": 51,
-    "v": 46,
-    "x": 59,
-    "y": 48,
-    "z": 36,
-    "|": 18,
-    "Ñ": 45,
-    "á": 52,
-    "é": 33,
-    "í": 2,
-    "ñ": 26,
-    "ú": 24,
-    "Ɨ": 28,
-    "ɨ": 50,
-    "ˈ": 8,
-    "’": 53,
-    "…": 7
-  }
-}
+{"meh": {"i": 0, "e": 1, "\u00ed": 2, ".": 3, "S": 4, "m": 5, "N": 6, "\u2026": 7, "\u02c8": 8, "f": 9, "D": 10, "r": 11, "U": 12, "K": 13, "E": 14, "c": 15, "a": 16, "A": 17, "P": 19, "q": 20, "'": 21, "T": 22, "l": 23, "\u00fa": 24, "Y": 25, "\u00f1": 26, "I": 27, "\u0197": 28, "s": 29, "V": 30, "k": 31, "p": 32, "\u00e9": 33, "h": 34, "j": 35, "z": 36, "b": 37, "d": 38, "W": 39, "M": 40, "L": 41, "R": 42, "X": 43, "o": 44, "\u00d1": 45, "v": 46, "O": 47, "y": 48, "n": 49, "\u0268": 50, "u": 51, "\u00e1": 52, "\u2019": 53, "t": 54, "F": 55, "J": 56, "H": 57, "g": 58, "x": 59, "|": 18, "...": 60, "[UNK]": 61, "[PAD]": 62}}